© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 6774
    Prev
    Next
    INDEX
    Explanations

    words and phrases that represent advancement and evolution

    oai_token-act-pair · gemini-2.0-flash

    "as" in many languages

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     disambiguazione
    -1.05
    GEBURTSDATUM
    -0.93
    تقاوى
    -0.88
     AssemblyCompany
    -0.86
    évaluateur
    -0.79
    oredCriteria
    -0.76
     >=",
    -0.67
     كومونز
    -0.66
     متعلقه
    -0.64
    Personendaten
    -0.63
    POSITIVE LOGITS
     as
    2.80
     sebagai
    1.73
    作为
    1.44
    作為
    1.33
     jako
    1.33
    sebagai
    1.32
     как
    1.30
     ως
    1.28
     као
    1.27
     Sebagai
    1.20
    Activations Density 4.180%

    No Known Activations